summaryrefslogtreecommitdiffstats
path: root/sys/net/if_tun.c
blob: e00ce0c5bd3d0c4b3afaf25d41908678dc1316e2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
/*	$NetBSD: if_tun.c,v 1.14 1994/06/29 06:36:25 cgd Exp $	*/

/*
 * Copyright (c) 1988, Julian Onions <jpo@cs.nott.ac.uk>
 * Nottingham University 1987.
 *
 * This source may be freely distributed, however I would be interested
 * in any changes that are made.
 *
 * This driver takes packets off the IP i/f and hands them up to a
 * user process to have its wicked way with. This driver has it's
 * roots in a similar driver written by Phil Cockcroft (formerly) at
 * UCL. This driver is based much more on read/write/poll mode of
 * operation though.
 */

#include "tun.h"
#if NTUN > 0

#include "opt_devfs.h"
#include "opt_inet.h"

#include <sys/param.h>
#include <sys/proc.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/filio.h>
#include <sys/sockio.h>
#include <sys/ttycom.h>
#include <sys/poll.h>
#include <sys/signalvar.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#ifdef DEVFS
#include <sys/devfsext.h>
#endif /*DEVFS*/
#include <sys/conf.h>
#include <sys/uio.h>
/*
 * XXX stop <sys/vnode.h> from including <vnode_if.h>.  <vnode_if.h> doesn't
 * exist if we are an LKM.
 */
#undef KERNEL
#include <sys/vnode.h>
#define KERNEL

#include <net/if.h>
#include <net/netisr.h>
#include <net/route.h>

#ifdef INET
#include <netinet/in.h>
#include <netinet/in_var.h>
#endif

#ifdef NS
#include <netns/ns.h>
#include <netns/ns_if.h>
#endif

#include "bpfilter.h"
#if NBPFILTER > 0
#include <net/bpf.h>
#endif

#include <net/if_tunvar.h>
#include <net/if_tun.h>

static void tunattach __P((void *));
PSEUDO_SET(tunattach, if_tun);

#define TUNDEBUG	if (tundebug) printf
static int tundebug = 0;
SYSCTL_INT(_debug, OID_AUTO, if_tun_debug, CTLFLAG_RW, &tundebug, 0, "");

static struct tun_softc tunctl[NTUN];

static int tunoutput __P((struct ifnet *, struct mbuf *, struct sockaddr *,
	    struct rtentry *rt));
static int tunifioctl __P((struct ifnet *, u_long, caddr_t));
static int tuninit __P((int));

static	d_open_t	tunopen;
static	d_close_t	tunclose;
static	d_read_t	tunread;
static	d_write_t	tunwrite;
static	d_ioctl_t	tunioctl;
static	d_poll_t	tunpoll;

#define CDEV_MAJOR 52
static struct cdevsw tun_cdevsw = {
	tunopen,	tunclose,	tunread,	tunwrite,
	tunioctl,	nullstop,	noreset,	nodevtotty,
	tunpoll,	nommap,		nostrategy,	"tun",	NULL,	-1
};


static	int	tun_devsw_installed;
#ifdef	DEVFS
static	void	*tun_devfs_token[NTUN];
#endif

#define minor_val(n) ((((n) & ~0xff) << 8) | ((n) & 0xff))
#define dev_val(n) (((n) >> 8) | ((n) & 0xff))

static void
tunattach(dummy)
	void *dummy;
{
	register int i;
	struct ifnet *ifp;
	dev_t dev;

	if ( tun_devsw_installed )
		return;
	dev = makedev(CDEV_MAJOR, 0);
	cdevsw_add(&dev, &tun_cdevsw, NULL);
	tun_devsw_installed = 1;
	for ( i = 0; i < NTUN; i++ ) {
#ifdef DEVFS
		tun_devfs_token[i] = devfs_add_devswf(&tun_cdevsw, minor_val(i),
						      DV_CHR, UID_UUCP,
						      GID_DIALER, 0600,
						      "tun%d", i);
#endif
		tunctl[i].tun_flags = TUN_INITED;

		ifp = &tunctl[i].tun_if;
		ifp->if_unit = i;
		ifp->if_name = "tun";
		ifp->if_mtu = TUNMTU;
		ifp->if_ioctl = tunifioctl;
		ifp->if_output = tunoutput;
		ifp->if_flags = IFF_POINTOPOINT | IFF_MULTICAST;
		ifp->if_snd.ifq_maxlen = ifqmaxlen;
		if_attach(ifp);
#if NBPFILTER > 0
		bpfattach(ifp, DLT_NULL, sizeof(u_int));
#endif
	}
}

/*
 * tunnel open - must be superuser & the device must be
 * configured in
 */
static	int
tunopen(dev, flag, mode, p)
	dev_t	dev;
	int	flag, mode;
	struct proc *p;
{
	struct ifnet	*ifp;
	struct tun_softc *tp;
	register int	unit, error;

	error = suser(p->p_ucred, &p->p_acflag);
	if (error)
		return (error);

	if ((unit = dev_val(minor(dev))) >= NTUN)
		return (ENXIO);
	tp = &tunctl[unit];
	if (tp->tun_flags & TUN_OPEN)
		return EBUSY;
	ifp = &tp->tun_if;
	tp->tun_flags |= TUN_OPEN;
	TUNDEBUG("%s%d: open\n", ifp->if_name, ifp->if_unit);
	return (0);
}

/*
 * tunclose - close the device - mark i/f down & delete
 * routing info
 */
static	int
tunclose(dev, foo, bar, p)
	dev_t dev;
	int foo;
	int bar;
	struct proc *p;
{
	register int	unit = dev_val(minor(dev)), s;
	struct tun_softc *tp = &tunctl[unit];
	struct ifnet	*ifp = &tp->tun_if;
	struct mbuf	*m;

	tp->tun_flags &= ~TUN_OPEN;

	/*
	 * junk all pending output
	 */
	do {
		s = splimp();
		IF_DEQUEUE(&ifp->if_snd, m);
		splx(s);
		if (m)
			m_freem(m);
	} while (m);

	if (ifp->if_flags & IFF_UP) {
		s = splimp();
		if_down(ifp);
		if (ifp->if_flags & IFF_RUNNING) {
		    /* find internet addresses and delete routes */
		    register struct ifaddr *ifa;
		    for (ifa = ifp->if_addrhead.tqh_first; ifa;
			 ifa = ifa->ifa_link.tqe_next) {
			if (ifa->ifa_addr->sa_family == AF_INET) {
			    rtinit(ifa, (int)RTM_DELETE,
				   tp->tun_flags & TUN_DSTADDR ? RTF_HOST : 0);
			}
		    }
		}
		splx(s);
	}
	tp->tun_pgrp = 0;
	selwakeup(&tp->tun_rsel);

	TUNDEBUG ("%s%d: closed\n", ifp->if_name, ifp->if_unit);
	return (0);
}

static int
tuninit(unit)
	int	unit;
{
	struct tun_softc *tp = &tunctl[unit];
	struct ifnet	*ifp = &tp->tun_if;
	register struct ifaddr *ifa;

	TUNDEBUG("%s%d: tuninit\n", ifp->if_name, ifp->if_unit);

	ifp->if_flags |= IFF_UP | IFF_RUNNING;
	getmicrotime(&ifp->if_lastchange);

	for (ifa = ifp->if_addrhead.tqh_first; ifa; 
	     ifa = ifa->ifa_link.tqe_next) {
#ifdef INET
		if (ifa->ifa_addr->sa_family == AF_INET) {
		    struct sockaddr_in *si;

		    si = (struct sockaddr_in *)ifa->ifa_addr;
		    if (si && si->sin_addr.s_addr)
			    tp->tun_flags |= TUN_IASET;

		    si = (struct sockaddr_in *)ifa->ifa_dstaddr;
		    if (si && si->sin_addr.s_addr)
			    tp->tun_flags |= TUN_DSTADDR;
		}
#endif
	}
	return 0;
}

/*
 * Process an ioctl request.
 */
int
tunifioctl(ifp, cmd, data)
	struct ifnet *ifp;
	u_long	cmd;
	caddr_t	data;
{
	register struct ifreq *ifr = (struct ifreq *)data;
	int		error = 0, s;

	s = splimp();
	switch(cmd) {
	case SIOCSIFADDR:
		tuninit(ifp->if_unit);
		TUNDEBUG("%s%d: address set\n",
			 ifp->if_name, ifp->if_unit);
		break;
	case SIOCSIFDSTADDR:
		tuninit(ifp->if_unit);
		TUNDEBUG("%s%d: destination address set\n",
			 ifp->if_name, ifp->if_unit);
		break;
	case SIOCSIFMTU:
		ifp->if_mtu = ifr->ifr_mtu;
		TUNDEBUG("%s%d: mtu set\n",
			 ifp->if_name, ifp->if_unit);
		break;
	case SIOCADDMULTI:
	case SIOCDELMULTI:
		break;


	default:
		error = EINVAL;
	}
	splx(s);
	return (error);
}

/*
 * tunoutput - queue packets from higher level ready to put out.
 */
int
tunoutput(ifp, m0, dst, rt)
	struct ifnet   *ifp;
	struct mbuf    *m0;
	struct sockaddr *dst;
	struct rtentry *rt;
{
	struct tun_softc *tp = &tunctl[ifp->if_unit];
	struct proc	*p;
	int		s;

	TUNDEBUG ("%s%d: tunoutput\n", ifp->if_name, ifp->if_unit);

	if ((tp->tun_flags & TUN_READY) != TUN_READY) {
		TUNDEBUG ("%s%d: not ready 0%o\n", ifp->if_name,
			  ifp->if_unit, tp->tun_flags);
		m_freem (m0);
		return EHOSTDOWN;
	}

#if NBPFILTER > 0
	/* BPF write needs to be handled specially */
	if (dst->sa_family == AF_UNSPEC) {
		dst->sa_family = *(mtod(m0, int *));
		m0->m_len -= sizeof(int);
		m0->m_pkthdr.len -= sizeof(int);
		m0->m_data += sizeof(int);
	}

	if (ifp->if_bpf) {
		/*
		 * We need to prepend the address family as
		 * a four byte field.  Cons up a dummy header
		 * to pacify bpf.  This is safe because bpf
		 * will only read from the mbuf (i.e., it won't
		 * try to free it or keep a pointer to it).
		 */
		struct mbuf m;
		u_int af = dst->sa_family;

		m.m_next = m0;
		m.m_len = 4;
		m.m_data = (char *)&af;

		bpf_mtap(ifp, &m);
	}
#endif

	switch(dst->sa_family) {
#ifdef INET
	case AF_INET:
		s = splimp();
		if (IF_QFULL(&ifp->if_snd)) {
			IF_DROP(&ifp->if_snd);
			m_freem(m0);
			splx(s);
			ifp->if_collisions++;
			return (ENOBUFS);
		}
		ifp->if_obytes += m0->m_pkthdr.len;
		IF_ENQUEUE(&ifp->if_snd, m0);
		splx(s);
		ifp->if_opackets++;
		break;
#endif
	default:
		m_freem(m0);
		return EAFNOSUPPORT;
	}

	if (tp->tun_flags & TUN_RWAIT) {
		tp->tun_flags &= ~TUN_RWAIT;
		wakeup((caddr_t)tp);
	}
	if (tp->tun_flags & TUN_ASYNC && tp->tun_pgrp) {
		if (tp->tun_pgrp > 0)
			gsignal(tp->tun_pgrp, SIGIO);
		else if ((p = pfind(-tp->tun_pgrp)) != 0) 
			psignal(p, SIGIO);
	}
	selwakeup(&tp->tun_rsel);
	return 0;
}

/*
 * the cdevsw interface is now pretty minimal.
 */
static	int
tunioctl(dev, cmd, data, flag, p)
	dev_t		dev;
	u_long		cmd;
	caddr_t		data;
	int		flag;
	struct proc	*p;
{
	int		unit = dev_val(minor(dev)), s;
	struct tun_softc *tp = &tunctl[unit];
 	struct tuninfo *tunp;

	switch (cmd) {
 	case TUNSIFINFO:
 	        tunp = (struct tuninfo *)data;
 		tp->tun_if.if_mtu = tunp->mtu;
 		tp->tun_if.if_type = tunp->type;
 		tp->tun_if.if_baudrate = tunp->baudrate;
 		break;
 	case TUNGIFINFO:
 		tunp = (struct tuninfo *)data;
 		tunp->mtu = tp->tun_if.if_mtu;
 		tunp->type = tp->tun_if.if_type;
 		tunp->baudrate = tp->tun_if.if_baudrate;
 		break;
	case TUNSDEBUG:
		tundebug = *(int *)data;
		break;
	case TUNGDEBUG:
		*(int *)data = tundebug;
		break;
	case FIONBIO:
		break;
	case FIOASYNC:
		if (*(int *)data)
			tp->tun_flags |= TUN_ASYNC;
		else
			tp->tun_flags &= ~TUN_ASYNC;
		break;
	case FIONREAD:
		s = splimp();
		if (tp->tun_if.if_snd.ifq_head) {
			struct mbuf *mb = tp->tun_if.if_snd.ifq_head;
			for( *(int *)data = 0; mb != 0; mb = mb->m_next) 
				*(int *)data += mb->m_len;
		} else
			*(int *)data = 0;
		splx(s);
		break;
	case TIOCSPGRP:
		tp->tun_pgrp = *(int *)data;
		break;
	case TIOCGPGRP:
		*(int *)data = tp->tun_pgrp;
		break;
	default:
		return (ENOTTY);
	}
	return (0);
}

/*
 * The cdevsw read interface - reads a packet at a time, or at
 * least as much of a packet as can be read.
 */
static	int
tunread(dev, uio, flag)
	dev_t dev;
	struct uio *uio;
	int flag;
{
	int		unit = dev_val(minor(dev));
	struct tun_softc *tp = &tunctl[unit];
	struct ifnet	*ifp = &tp->tun_if;
	struct mbuf	*m, *m0;
	int		error=0, len, s;

	TUNDEBUG ("%s%d: read\n", ifp->if_name, ifp->if_unit);
	if ((tp->tun_flags & TUN_READY) != TUN_READY) {
		TUNDEBUG ("%s%d: not ready 0%o\n", ifp->if_name,
			  ifp->if_unit, tp->tun_flags);
		return EHOSTDOWN;
	}

	tp->tun_flags &= ~TUN_RWAIT;

	s = splimp();
	do {
		IF_DEQUEUE(&ifp->if_snd, m0);
		if (m0 == 0) {
			if (flag & IO_NDELAY) {
				splx(s);
				return EWOULDBLOCK;
			}
			tp->tun_flags |= TUN_RWAIT;
			if( error = tsleep((caddr_t)tp, PCATCH | (PZERO + 1),
					"tunread", 0)) {
				splx(s);
				return error;
			}
		}
	} while (m0 == 0);
	splx(s);

	while (m0 && uio->uio_resid > 0 && error == 0) {
		len = min(uio->uio_resid, m0->m_len);
		if (len == 0)
			break;
		error = uiomove(mtod(m0, caddr_t), len, uio);
		MFREE(m0, m);
		m0 = m;
	}

	if (m0) {
		TUNDEBUG("Dropping mbuf\n");
		m_freem(m0);
	}
	return error;
}

/*
 * the cdevsw write interface - an atomic write is a packet - or else!
 */
static	int
tunwrite(dev, uio, flag)
	dev_t dev;
	struct uio *uio;
	int flag;
{
	int		unit = dev_val(minor(dev));
	struct ifnet	*ifp = &tunctl[unit].tun_if;
	struct mbuf	*top, **mp, *m;
	int		error=0, s, tlen, mlen;

	TUNDEBUG("%s%d: tunwrite\n", ifp->if_name, ifp->if_unit);

	if (uio->uio_resid < 0 || uio->uio_resid > TUNMRU) {
		TUNDEBUG("%s%d: len=%d!\n", ifp->if_name, ifp->if_unit,
		    uio->uio_resid);
		return EIO;
	}
	tlen = uio->uio_resid;

	/* get a header mbuf */
	MGETHDR(m, M_DONTWAIT, MT_DATA);
	if (m == NULL)
		return ENOBUFS;
	mlen = MHLEN;

	top = 0;
	mp = &top;
	while (error == 0 && uio->uio_resid > 0) {
		m->m_len = min(mlen, uio->uio_resid);
		error = uiomove(mtod (m, caddr_t), m->m_len, uio);
		*mp = m;
		mp = &m->m_next;
		if (uio->uio_resid > 0) {
			MGET (m, M_DONTWAIT, MT_DATA);
			if (m == 0) {
				error = ENOBUFS;
				break;
			}
			mlen = MLEN;
		}
	}
	if (error) {
		if (top)
			m_freem (top);
		return error;
	}

	top->m_pkthdr.len = tlen;
	top->m_pkthdr.rcvif = ifp;

#if NBPFILTER > 0
	if (ifp->if_bpf) {
		/*
		 * We need to prepend the address family as
		 * a four byte field.  Cons up a dummy header
		 * to pacify bpf.  This is safe because bpf
		 * will only read from the mbuf (i.e., it won't
		 * try to free it or keep a pointer to it).
		 */
		struct mbuf m;
		u_int af = AF_INET;

		m.m_next = top;
		m.m_len = 4;
		m.m_data = (char *)&af;

		bpf_mtap(ifp, &m);
	}
#endif

#ifdef INET
	s = splimp();
	if (IF_QFULL (&ipintrq)) {
		IF_DROP(&ipintrq);
		splx(s);
		ifp->if_collisions++;
		m_freem(top);
		return ENOBUFS;
	}
	IF_ENQUEUE(&ipintrq, top);
	splx(s);
	ifp->if_ibytes += tlen;
	ifp->if_ipackets++;
	schednetisr(NETISR_IP);
#endif
	return error;
}

/*
 * tunpoll - the poll interface, this is only useful on reads
 * really. The write detect always returns true, write never blocks
 * anyway, it either accepts the packet or drops it.
 */
static	int
tunpoll(dev, events, p)
	dev_t dev;
	int events;
	struct proc *p;
{
	int		unit = dev_val(minor(dev)), s;
	struct tun_softc *tp = &tunctl[unit];
	struct ifnet	*ifp = &tp->tun_if;
	int		revents = 0;

	s = splimp();
	TUNDEBUG("%s%d: tunpoll\n", ifp->if_name, ifp->if_unit);

	if (events & (POLLIN | POLLRDNORM))
		if (ifp->if_snd.ifq_len > 0) {
			TUNDEBUG("%s%d: tunpoll q=%d\n", ifp->if_name,
			    ifp->if_unit, ifp->if_snd.ifq_len);
			revents |= events & (POLLIN | POLLRDNORM);
		} else {
			TUNDEBUG("%s%d: tunpoll waiting\n", ifp->if_name,
			    ifp->if_unit);
			selrecord(p, &tp->tun_rsel);
		}

	if (events & (POLLOUT | POLLWRNORM))
		revents |= events & (POLLOUT | POLLWRNORM);

	splx(s);
	return (revents);
}


#endif  /* NTUN */
OpenPOWER on IntegriCloud